A two-stream framework with multi-channel self-attention is claimed to improve action recognition, but the zero-shot claim is not supported by any experimental results.
In: Proceedings of the IEEE International Conference on Computer Vision, ICCV (2015)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework
A two-stream framework with multi-channel self-attention is claimed to improve action recognition, but the zero-shot claim is not supported by any experimental results.